{
  "best_global_step": 500,
  "best_metric": 1.4127447605133057,
  "best_model_checkpoint": "./gemma3_finetune/checkpoint-500",
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 558,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.6064836978912354,
      "learning_rate": 1.6964285714285715e-05,
      "loss": 2.1903,
      "step": 20
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.9092773199081421,
      "learning_rate": 3.4821428571428574e-05,
      "loss": 1.8574,
      "step": 40
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.7761135101318359,
      "learning_rate": 4.999559412596081e-05,
      "loss": 1.6196,
      "step": 60
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 0.6488329768180847,
      "learning_rate": 4.974147171991723e-05,
      "loss": 1.5175,
      "step": 80
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 0.6469504237174988,
      "learning_rate": 4.910026034587031e-05,
      "loss": 1.4836,
      "step": 100
    },
    {
      "epoch": 0.5387205387205387,
      "eval_loss": 1.5036908388137817,
      "eval_runtime": 14.2727,
      "eval_samples_per_second": 87.65,
      "eval_steps_per_second": 11.0,
      "step": 100
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.7555330395698547,
      "learning_rate": 4.808199197976157e-05,
      "loss": 1.4586,
      "step": 120
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 0.7224211096763611,
      "learning_rate": 4.670259778589074e-05,
      "loss": 1.4615,
      "step": 140
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 0.7545987963676453,
      "learning_rate": 4.498365886828511e-05,
      "loss": 1.4429,
      "step": 160
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.6888415217399597,
      "learning_rate": 4.295206862678802e-05,
      "loss": 1.4457,
      "step": 180
    },
    {
      "epoch": 1.0754208754208754,
      "grad_norm": 0.7888140678405762,
      "learning_rate": 4.063961200042368e-05,
      "loss": 1.4164,
      "step": 200
    },
    {
      "epoch": 1.0754208754208754,
      "eval_loss": 1.450657606124878,
      "eval_runtime": 14.314,
      "eval_samples_per_second": 87.397,
      "eval_steps_per_second": 10.968,
      "step": 200
    },
    {
      "epoch": 1.183164983164983,
      "grad_norm": 0.7697953581809998,
      "learning_rate": 3.8082468180922686e-05,
      "loss": 1.4052,
      "step": 220
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 0.7794164419174194,
      "learning_rate": 3.532064457662889e-05,
      "loss": 1.4016,
      "step": 240
    },
    {
      "epoch": 1.3986531986531987,
      "grad_norm": 0.7602345943450928,
      "learning_rate": 3.239735088262007e-05,
      "loss": 1.3902,
      "step": 260
    },
    {
      "epoch": 1.5063973063973064,
      "grad_norm": 0.7201767563819885,
      "learning_rate": 2.935832304993402e-05,
      "loss": 1.3978,
      "step": 280
    },
    {
      "epoch": 1.614141414141414,
      "grad_norm": 0.7935007214546204,
      "learning_rate": 2.625110773063754e-05,
      "loss": 1.3875,
      "step": 300
    },
    {
      "epoch": 1.614141414141414,
      "eval_loss": 1.4275208711624146,
      "eval_runtime": 14.2116,
      "eval_samples_per_second": 88.027,
      "eval_steps_per_second": 11.047,
      "step": 300
    },
    {
      "epoch": 1.7218855218855218,
      "grad_norm": 0.746303379535675,
      "learning_rate": 2.312431839384543e-05,
      "loss": 1.393,
      "step": 320
    },
    {
      "epoch": 1.8296296296296295,
      "grad_norm": 0.7554110884666443,
      "learning_rate": 2.0026874751013972e-05,
      "loss": 1.3853,
      "step": 340
    },
    {
      "epoch": 1.9373737373737374,
      "grad_norm": 0.735357403755188,
      "learning_rate": 1.7007237389966146e-05,
      "loss": 1.3835,
      "step": 360
    },
    {
      "epoch": 2.043097643097643,
      "grad_norm": 0.7572635412216187,
      "learning_rate": 1.4112649592066293e-05,
      "loss": 1.369,
      "step": 380
    },
    {
      "epoch": 2.1508417508417508,
      "grad_norm": 0.7531948685646057,
      "learning_rate": 1.1388398194579725e-05,
      "loss": 1.3724,
      "step": 400
    },
    {
      "epoch": 2.1508417508417508,
      "eval_loss": 1.4167424440383911,
      "eval_runtime": 14.2716,
      "eval_samples_per_second": 87.657,
      "eval_steps_per_second": 11.001,
      "step": 400
    },
    {
      "epoch": 2.2585858585858585,
      "grad_norm": 0.7567663192749023,
      "learning_rate": 8.877105062283609e-06,
      "loss": 1.3674,
      "step": 420
    },
    {
      "epoch": 2.366329966329966,
      "grad_norm": 0.7656159400939941,
      "learning_rate": 6.618060253503472e-06,
      "loss": 1.3686,
      "step": 440
    },
    {
      "epoch": 2.474074074074074,
      "grad_norm": 0.7571391463279724,
      "learning_rate": 4.646607313425419e-06,
      "loss": 1.3617,
      "step": 460
    },
    {
      "epoch": 2.581818181818182,
      "grad_norm": 0.7939226627349854,
      "learning_rate": 2.9935903119851757e-06,
      "loss": 1.3648,
      "step": 480
    },
    {
      "epoch": 2.6895622895622897,
      "grad_norm": 0.7923122048377991,
      "learning_rate": 1.6848712776191767e-06,
      "loss": 1.3694,
      "step": 500
    },
    {
      "epoch": 2.6895622895622897,
      "eval_loss": 1.4127447605133057,
      "eval_runtime": 14.3897,
      "eval_samples_per_second": 86.937,
      "eval_steps_per_second": 10.911,
      "step": 500
    },
    {
      "epoch": 2.7973063973063974,
      "grad_norm": 0.7516689896583557,
      "learning_rate": 7.409255767952538e-07,
      "loss": 1.3562,
      "step": 520
    },
    {
      "epoch": 2.905050505050505,
      "grad_norm": 0.751866340637207,
      "learning_rate": 1.7652156975161982e-07,
      "loss": 1.3503,
      "step": 540
    }
  ],
  "logging_steps": 20,
  "max_steps": 558,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.181275398144e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}